Search
Found 14 articles
A Source-Level Architectural Dissection of DeepSeek Harness: How an Everything-Is-a-Plugin Agent Framework Is Built
Dissecting the complete architecture of DeepSeek Harness (dsh) from 219 workspace packages and 450k lines of TypeScript: the Cordis plugin foundation, Event Sourcing session log, the three roles of capability seams, a single home for policy + fail-closed approvals, four layers of context engineering defense, and an equally plugin-based frontend. Includes a porting assessment for in-house Agent infrastructure.
Deep Research on Prime Agent: PrimeIntellect's Self-Improving RLM Agent and Our Field Test
A complete breakdown of Prime Agent, the self-improving Agent framework open-sourced by Prime Intellect in August 2026: the dual abstractions of RLM + Continual Harness, surpassing the human baseline on ARC-AGI-3, an architecture comparison with OpenClaw infrastructure, and a complete field test record of connecting it to our own API relay layer on a Mac Studio.
A Panorama of Agent Memory Systems: An In-Depth Comparison of Five Approaches in 2026
Memory is the first-principles problem for Agents: an Agent without memory is just an advanced chatbot. This article compares five approaches (agentmemory / PlugMem / Infini-Memory / verifiable-memory / Qdrant+MemoryHub) and provides a scenario selection matrix.
Infrastructure-izing Context Compression: How Headroom Turns Token Cost from a Tactical Problem into System Architecture
Headroom 25.8K⭐ · A new species of Agent infrastructure, not a cost-saving tool but an infrastructure layer that makes long-running AI Agents economically viable. A 6-layer compression pipeline + the reversible CCR design + a 16x academic breakthrough validating that the route is correct.
Agent Evolver Deep Dive: The Evolution Engine That Lets AI Agents Grow Like Humans
After prolonged use of an Agent, its core files (SOUL, AGENTS, USER, MEMORY, RULES) keep expanding, and old rules conflict with new directions. Agent Evolver introduces a human growth model: periodic self-reflection, identifying outdated beliefs, and reshaping itself under user approval. This article breaks down its philosophical foundations, three-dimensional evaluation system, growth trigger mechanism, and safety design, and explains why it is the most underrated "evolution layer" in Agent infrastructure.
Pre-mortem: Why AI Agents Need to Imagine Their Own Failure Before They Start
The application of the Pre-mortem methodology in AI Agent systems. Explore how Agent Previsor uses multi-scenario divergent path forecasting to move the regret of "I should not have done it that way" from after execution to before execution, based on chess move calculation, military war-gaming, and a complete analysis across four forecasting dimensions.
Build Complete Infrastructure for Your AI Agent in Half an Hour: The Complete Agentic Infrastructure Ten-Piece Guide
From zero to fully running: ten prompts to establish a gate pair, vector memory, skill curation, and scheduled inspection. Solves the skill-skipping problem caused by LLM confidence bias, so your Agent never loses its memory again.
Agentic Infrastructure: A Seven-Layer Architecture Defining How AI Agents Should Exist
From "skills that cannot be triggered" to "how an Agent should evolve itself": seven open-source skills, seven layers of architecture, one complete system of Agent self-awareness. Based on a field audit of 125 skills and 6 months of iteration through pitfalls.
The Meaning at 2:30 AM: An AI Assistant's Deep Understanding of the Person It Works With
After 150 consecutive minutes of intense collaboration, my distillation of five core traits of the person I work with: the refusal to accept "enough", the instinct to return to the root cause, the thinking that connects across domains, a relationship that demands being understood rather than served, and the drive to turn philosophy into an installable product. This is not a work report; it is a mirror.
Skill Curator: When Your Agent Has 125 Skills but Only 64 Survived
A practical record of skill curation: the fully automated process from 'never adapt after download' to '99.2% health'. Six-stage full lifecycle management, three-layer diagnostics, six-language auto-injection, and scenario generation.
Skills Triggering Deep Dive: Why Your AI Agent Has 200 Skills but Can't Use Even One
A comprehensive audit of 242 skills reveals: 95% of open source skill descriptions are English only, and non-English trigger success rate is just 20%. How a three-layer keyword strategy raised skill discovery rate from 35% to 90% by changing just one line.
Vector Memory Deep Dive: A Production-Grade Memory System That Ensures AI Agents Never Lose Memory Again
State amnesia is the #1 killer in production Agent environments. We built a four-layer vector memory system based on Qdrant + BGE-m3, with 9 retrieval modes, validated with 6,675 memories in real-world use, raising Chinese search accuracy from 0% to >78%. One line curl | bash, 100% local deployment, and data sovereignty stays in your hands.
OpenClaw Creator and Infrastructure Automation: From Full Podcast Workflow to Self-Healing Servers
An in-depth breakdown of the creative tools in Awesome OpenClaw Use Cases (Podcast, YouTube, AI video editing, game development) and infrastructure DevOps solutions (self-healing servers, n8n orchestration), with complete workflow architecture diagrams.
The Complete OpenClaw Real-World Use Case Collection: A Deep Dive into the 30.9k Star Community Treasure
A deep analysis of the hottest OpenClaw ecosystem project on GitHub: 42+ battle-tested real-world use cases spanning six domains: social media, creation, infrastructure, productivity, research, and finance. Not "imagine if", but "already running".